README.md

metadata

language: en
tags: vae
license: apache-2.0

T5-VAE-Wiki (flax)

A Transformer-VAE made using flax.

Try the [demo] (TODO)!

It has been trained to interpolate on sentences form wikipedia.

Done as part of Huggingface community training (see forum post).

Builds on T5, using an autoencoder to convert it into an MMD-VAE (more info).

How to use from the 🤗/transformers library

Add model repo as a submodule:

git submodule add https://github.com/Fraser-Greenlee/t5-vae-flax.git t5_vae_flax

from transformers import AutoTokenizer
from t5_vae_flax.src.t5_vae import FlaxT5VaeForAutoencoding

tokenizer = AutoTokenizer.from_pretrained("t5-base")

model = FlaxT5VaeForAutoencoding.from_pretrained("flax-community/t5-vae-python")

Setup

Run setup_tpu_vm_venv.sh to setup a virtual enviroment on a TPU VM for training.